Mobile AutomationSAFE
Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge
Overview
Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge
6b4afc353bc7OBSERVED · 2026-10-12Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: mobile-automation description: FlutterアプリのUI動作をシミュレーターで検証する、またはBridgeとのE2Eを確認するときに使う。 --- # Mobile Automation 検証対象に応じて必要な参照だけ読む。dart-mcp / Marionette で実行時の状態を確認する。 - 起動・接続・CLIとMCPの使い分け: [references/startup.md](references/startup.md) - Bridge不要のMock UI検証と要素キー: [references/mock-and-keys.md](references/mock-and-keys.md) - 実際のBridge通信を含む検証: [references/e2e.md](references/e2e.md) - 接続・ジェスチャー・モック制限の問題: [references/troubleshooting.md](references/troubleshooting.md) ## 実行範囲 - 既定はiOSシミュレーターとテスト用Bridge `8766`。ユーザーが指定したデバイス・接続先を優先する。本番 `8765` のプロセスを停止しない。 - プロジェクトルートは `git rev-parse --show-toplevel`、アプリはその配下の `apps/mobile`。 - 検証する挙動と期待結果を決め、関連するシナリオを選ぶ。単純なUI確認は直接操作する。複数画面の独立した検証は、利用可能なら `e2e-verifier` 等へ委譲できる。 - 操作には現在の `get_interactive_elements` のキー・boundsを使う。画面遷移やジェスチャー後は結果を確認する。 - 要素・ログで挙動を確認し、外観・レイアウトの変更はスクリーンショットで目視する。枚数は検証対象に応じて選ぶ。 - 終了時は自分が起動したアプリ・BridgeだけPIDを指定して停止する。プレビュー継続を依頼されている場合は残し、接続方法を報告する。 - 検証結果と未確認の範囲を報告する。Mock表示の成功を実通信の成功として扱わない。
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
.agents/skills
AGENTS.md
Gates applied: no_behavioural_pass.
6b4afc353bc7full audit observations/trust-audit/skill/k9i-0__mobile-automation.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 6b4afc353bc7 | SAFE | B | 89 | first audit |
Questions
What does the Mobile Automation skill do?
Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge
Is Mobile Automation safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Mobile Automation access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Mobile Automation work with?
Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (6b4afc353bc7), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.